Rotating end face speed detection system and method based on computer vision

Abstract

The invention discloses a rotating end face speed detection system and method based on computer vision, and belongs to the technical field of computer vision. The rotating end face speed detection system based on computer vision comprises an image acquisition unit which is used for acquiring a video image containing a circular object in real time; the HSV parameter unit is used for manually setting HSV parameters; the target detection tracking unit is used for extracting the contour of the circular object and tracking the motion of the circular object; a speed calculation unit that calculates a rotation speed based on the angle change and the time difference; the display output unit is used for displaying a detection result in real time, and hardware of the system is based on a hardware system of an AI development board, a camera and a relay board; the core algorithm logic is deployed on the AI development board; wherein the image acquisition unit, namely the camera, is used for intensively acquiring circular motion of a cylindrical end face image color object.

Description

Technical Field

[0001] The present invention relates to the technical field of computer vision, and in particular to a rotation end face speed detection system and method based on computer vision. Background Art

[0002] Computer vision is a rapidly developing emerging discipline. Simulating human visual mechanisms to achieve measurement, positioning, and monitoring functions has become a key topic in the field of intelligent instruments. Over the past two decades, computer vision research has moved from the laboratory to practical applications, achieving significant progress, from simple binary image processing to multi-grayscale image processing, and from general two-dimensional information processing to the study of three-dimensional visual mechanisms, models, and algorithms. The rapid advancement of the computer industry and the development of disciplines such as artificial intelligence and neural networks have further promoted the widespread use of computer vision systems. Currently, computer vision systems are widely used in various fields, including visual inspection. A search revealed that Chinese patent publication No. CN1888912A discloses a computer vision-based speed measurement device, comprising a visual acquisition device, a speed measurement platform, an external trigger module, and a computer system. The visual acquisition device is used to capture motion-blurred images of an object mounted on the speed measurement platform and transmit the resulting blurred image information to the computer system. The computer system includes a control module, a display module, and a blurred image processing and speed measurement module. The blurred image information transmitted to the computer system is sent to the display module on one path and to the blurred image processing and speed measurement module on another path. The display module displays the acquired blurred image and information in real time. The blurred image processing and speed measurement module performs motion dimensionality reduction, time-frequency transformation, spectrum analysis, and motion parameter acquisition on the acquired blurred image to measure the rotational speed of the object being measured. The system of the present invention has a simple structure, good speed measurement results, and can be applied to various speed measurement situations.

[0003] Accurately detecting the speed of rotating objects is crucial in many fields, including industrial production and scientific research. Traditional speed detection methods, such as contact-type speed sensors, can easily interfere with rotating objects, affecting their normal operation and are complex to install. Non-contact methods such as radar speed measurement also suffer from high costs and limited accuracy. With the development of computer vision technology, using computer vision to detect the speed of rotating objects has become a new research direction. However, existing computer vision-based detection solutions often suffer from issues such as sensitivity to ambient light, difficulty in adaptively adjusting detection parameters, and low detection accuracy. Summary of the Invention

[0004] In order to solve the problems raised in the background technology, the present invention provides a rotating end surface speed detection system and method based on computer vision.

[0005] In view of the above problems, the technical solution proposed by the present invention is:

[0006] The rotating end surface speed detection system based on computer vision includes:

[0007] An image acquisition unit, used for acquiring video images containing circular objects in real time;

[0008] HSV parameter unit, manually set HSV parameters;

[0009] Target detection and tracking unit, used to extract the outline of circular objects and track their motion;

[0010] a speed calculation unit for calculating the rotation speed based on the angle change and the time difference;

[0011] Display output unit, used to display the detection results in real time.

[0012] As a preferred technical solution of the present invention, the hardware of the system is based on the hardware system of AI development board, camera, and relay board; the core algorithm logic is deployed on the AI ​​development board; wherein, the image acquisition unit, namely the camera, focuses on collecting the circular motion of the cylindrical end face image object.

[0013] As a preferred technical solution of the present invention, an image preprocessing module is provided inside the image acquisition unit, and the image preprocessing module includes: a Gaussian blur processing unit for reducing image noise; an HSV color space conversion unit for converting the image from the BGR color space to the HSV color space; and a dual threshold mask generation unit for processing red crossings in the HSV space.

[0014] As a preferred technical solution of the present invention, a target detection module is provided inside the target detection and tracking unit, and the target detection module includes: a detection unit for detecting contours in an image; a fitting unit for calculating the circumscribed circle of the contour; and a center point calculation unit for calculating the centroid of the contour.

[0015] As a preferred technical solution of the present invention, the speed calculation unit is internally provided with an angle calculation module and a time difference meter module.

[0016] The angle calculation module includes: an angle calculation unit for calculating the angle of the current point relative to the reference center point; an angle difference calculation unit for calculating the angle change between adjacent frames; and an angle span processing unit for processing the case where the angle spans 360 degrees;

[0017] The time difference meter module includes an angle buffer for storing angle changes of the latest N frames, a time buffer for storing time differences between adjacent frames, and an RPM calculation unit for calculating revolutions per minute based on the angle changes and the time differences.

[0018] As a preferred technical solution of the present invention, a display module is provided inside the display output unit, and the display module includes: a real-time image display unit for displaying the processed image, a speed display unit for displaying the calculated rotation speed, and a direction display unit for displaying the rotation direction.

[0019] In another aspect, the present invention provides a method for detecting the system, comprising the following steps:

[0020] S1. Initialize the camera and set the HSV color threshold parameters;

[0021] S2, real-time acquisition of video images and preprocessing;

[0022] S3, extract the target object through HSV color threshold segmentation;

[0023] S4, detecting and calculating the center position of the circular object;

[0024] S5. Calculate the angle of the current frame relative to the reference point;

[0025] S6. Update angle change and time difference information;

[0026] S7. Calculate and display the rotation speed.

[0027] Step S3 includes: calculating the angle of the current point relative to the reference center point; processing the case where the angle spans 360 degrees; and updating the angle buffer.

[0028] Wherein, the step S4 includes: performing Gaussian blur processing on the image; converting the image into HSV color space; applying a double threshold mask to extract the target object; and performing morphological operations to optimize the target area.

[0029] Wherein, the step S7 includes: calculating the RPM value based on the angle change and the time difference; applying a smoothing factor to optimize the calculation result; and displaying the calculation result in real time.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] This computer vision-based rotating end face speed detection system and method includes an image processing method: directly analyzing the angular changes of a clear image through HSV color segmentation and real-time feature point tracking; speed measurement: directly calculating the rotational speed through the length change rate of the intersection of the geometric shape of the speed measurement mark and the virtual center line, or calculating the rotation angle through the sampling time difference of the dual cameras; hardware: constructing a symmetrical arrangement of dual cameras through the technology of double threshold masks, expanding the measurement range and improving low-speed speed accuracy, and some solutions introduce a stroboscope to assist in shooting. Therefore, the present invention has the advantages of simple structure, easy implementation, accurate detection, and good real-time performance. It can be widely used in the fields of industrial equipment speed detection, mechanical transmission system monitoring, and moving object speed measurement, and has important practical value and promotion significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a data optimization framework diagram of the computer vision-based rotation end face velocity detection system and method provided by the present invention;

[0033] Figure 2 A parameter optimization flow chart of the computer vision-based rotation end face velocity detection system and method provided by the present invention;

[0034] Figure 3 A flow chart of speed calculation for the computer vision-based rotation end face speed detection system and method provided by the present invention;

[0035] Figure 4 This is a diagram of the actual operation interface of the system and method for detecting the rotation end face speed based on computer vision provided by the present invention. DETAILED DESCRIPTION

[0036] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0037] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the technical features indicated. Thus, features specified as "first" or "second" may explicitly or implicitly include one or more of such features; and in the description of this application, unless otherwise specified, "plurality" means two or more.

[0038] Example 1

[0039] Hardware Setup: Select an appropriate AI development board with powerful computing capabilities to quickly process image data and run core algorithms. Use a high-resolution camera, mounted at a suitable distance from the motor's rotating end face to ensure clear capture of the motor shaft's circular motion. The camera, acting as an image acquisition unit, is responsible for capturing real-time video images of the motor shaft's circular end face. Also connect a relay board for possible subsequent control operations.

[0040] System initialization: After starting the system, during the initialization phase, manually set the HSV color threshold parameters. This parameter is used to extract the target object (motor shaft end face) in subsequent images.

[0041] Image Acquisition and Preprocessing: The camera begins capturing real-time video images of the motor shaft end face. The image preprocessing module within the image acquisition unit begins processing. First, the captured image is processed using a Gaussian blur processing unit to effectively reduce image noise and enhance image clarity. The HSV color space conversion unit then converts the image from BGR to HSV color space, facilitating subsequent color-based target extraction. Finally, the dual-threshold mask generation unit generates a dual-threshold mask for any red crossings in the HSV space (assuming there is a red mark on the motor shaft end face for detection).

[0042] Target detection and tracking: The target detection module in the target detection and tracking unit starts working. The detection unit detects the contour in the image, the fitting unit calculates the circumscribed circle of the contour, and the center point calculation unit calculates the centroid of the contour, thereby accurately extracting the contour of the motor shaft end face and tracking its movement. Among them, the mean shift algorithm can be adapted: based on the color features of the target, the color histogram of the target area is calculated, and then the position where the color distribution of the target best matches the color distribution of the candidate area is searched iteratively to achieve target tracking.

[0043] Speed ​​Calculation and Display: The angle calculation module and time difference meter module in the speed calculation unit work together. The angle calculation unit calculates the angle of the current point relative to the reference center point, the angle difference calculation unit calculates the angle change between adjacent frames, and the angle span processing unit handles angle spans of 360 degrees. The angle buffer stores the angle changes of the last N frames, the time buffer stores the time difference between adjacent frames, and the RPM calculation unit calculates the motor's revolutions per minute (RPM) based on the angle change and time difference. The display module of the display output unit displays the processed image through the real-time image display unit. Simultaneously, the speed display unit displays the calculated motor rotation speed, and the direction display unit displays the motor's rotation direction.

[0044] Example 2

[0045] See also Figures 1-4

[0046] Hardware Deployment: Select an appropriate AI development board, ensuring its performance meets the requirements for processing pulley image data. Install a high-definition camera and adjust its position and angle to clearly capture the rotating end face of the pulley. Connect a relay board to control the transmission system when the pulley speed is abnormal.

[0047] Initialization: Turn on the system and set the HSV color threshold parameter according to the light conditions of the pulley working environment. This parameter is key to accurately extracting the pulley outline.

[0048] Image acquisition and preprocessing process: The camera continuously captures video images of the rotating end face of the pulley. The image preprocessing module within the image acquisition unit processes the images sequentially. The Gaussian blur processing unit removes noise interference from the image. The HSV color space conversion unit converts the image into the HSV color space. The dual-threshold mask generation unit generates a dual-threshold mask based on the crossing of the red mark (if any) on the pulley in the HSV space.

[0049] Target recognition and tracking: The target detection module of the target detection and tracking unit starts working. The detection unit searches for the contour in the image, the fitting unit calculates the circumscribed circle of the contour, and the center point calculation unit determines the contour centroid, thereby realizing the extraction of the pulley contour and motion tracking.

[0050] Speed ​​Calculation and Result Display: The angle calculation module and time difference meter module in the speed calculation unit are in action. The angle calculation module calculates the angle of the current point relative to the reference center point, the angle change between adjacent frames, and the angle spanning 360 degrees. The angle buffer and time buffer of the time difference meter module store the corresponding information, and the RPM calculation unit calculates the pulley speed based on this information. The display module of the display output unit presents the processed image, calculated pulley rotation speed, and rotation direction in real time, allowing operators to monitor the pulley's operating status in real time.

[0051] Specifically, the working principle of this computer vision-based rotating end face speed detection system and method is as follows: when in use, the image acquisition unit uses a high-resolution camera to capture video images of the rotating end face in real time at a certain frame rate; the captured image enters the image preprocessing module, first undergoes noise removal by the Gaussian blur processing unit, and then is converted from the BGR color space to the HSV color space by the HSV color space conversion unit. The dual-threshold mask generation unit generates a dual-threshold mask for the case where the color is discontinuous in the HSV space; then the target detection module of the target detection and tracking unit searches for the image contour, the fitting unit calculates the circumscribed circle, and the center point calculation unit determines the center of mass to achieve target detection and tracking; in the speed calculation unit, the angle calculation module calculates the angle of the current point relative to the reference center point, the angle change of adjacent frames, and handles the angle crossing situation; the angle buffer and time buffer of the time difference meter module respectively store relevant information; the RPM calculation unit converts the angular velocity into revolutions per minute; finally, the display module of the display output unit displays the processed image, and the speed display unit and direction display unit respectively display the rotation speed and direction. In addition, the system can also be connected to a relay board, and when a speed abnormality is detected, the control output unit triggers the relay for corresponding control.

[0052] In the several embodiments provided in this application, it should be understood that the disclosed systems, modules and methods can be implemented in other ways. For example, the module embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of modules or units, which can be electrical, mechanical or other forms.

[0053] The above embodiments are intended only to illustrate the technical solutions of the present application and are not intended to limit them. The present application is not limited to the precise structures described above and illustrated in the accompanying drawings, and it cannot be assumed that the specific implementation of the present application is limited to these descriptions. For those skilled in the art of the present application, any changes and modifications made without departing from the concept of the present application should be deemed to fall within the scope of protection of the present application.

Claims

1. The rotating end surface speed detection system based on computer vision is characterized by: include: An image acquisition unit, used for acquiring video images containing circular objects in real time; HSV parameter unit, manually set HSV parameters; Target detection and tracking unit, used to extract the outline of circular objects and track their motion; a speed calculation unit for calculating the rotation speed based on the angle change and the time difference; Display output unit, used to display the detection results in real time.

2. The computer vision-based rotation end surface velocity detection system according to claim 1, characterized in that: The hardware of this system is based on the hardware system of AI development board, camera, and relay board; The core algorithm logic is deployed on the AI ​​development board; The image acquisition unit, namely the camera, focuses on acquiring the circular motion of the cylindrical end surface image object.

3. The computer vision-based rotation end surface velocity detection system according to claim 1, characterized in that: An image preprocessing module is provided inside the image acquisition unit, which includes: a Gaussian blur processing unit for reducing image noise; an HSV color space conversion unit for converting the image from the BGR color space to the HSV color space; and a dual threshold mask generation unit for processing red crossings in the HSV space.

4. The computer vision-based rotation end surface velocity detection system according to claim 1, characterized in that: The target detection and tracking unit has a target detection module inside, and the target detection module includes: a detection unit for detecting the contour in the image; a fitting unit for calculating the circumscribed circle of the contour; and a center point calculation unit for calculating the centroid of the contour.

5. The computer vision-based rotation end surface velocity detection system according to claim 1, characterized in that: The speed calculation unit is internally provided with an angle calculation module and a time difference meter module. The angle calculation module includes: an angle calculation unit for calculating the angle of the current point relative to the reference center point; an angle difference calculation unit for calculating the angle change between adjacent frames; and an angle span processing unit for processing the case where the angle spans 360 degrees; The time difference meter module includes an angle buffer for storing angle changes of the latest N frames, a time buffer for storing time differences between adjacent frames, and an RPM calculation unit for calculating revolutions per minute based on the angle changes and the time differences.

6. The computer vision-based rotation end surface velocity detection system according to claim 1, characterized in that: A display module is provided inside the display output unit, and the display module includes: a real-time image display unit for displaying a processed image, a speed display unit for displaying a calculated rotation speed, and a direction display unit for displaying a rotation direction.

7. The detection method of the system according to any one of claims 1 to 6, characterized in that: The following steps are involved: S1. Initialize the camera and set the HSV color threshold parameters; S2, real-time acquisition of video images and preprocessing; S3, extract the target object through HSV color threshold segmentation; S4, detecting and calculating the center position of the circular object; S5. Calculate the angle of the current frame relative to the reference point; S6. Update angle change and time difference information; S7. Calculate and display the rotation speed.

8. The detection method according to claim 7, characterized in that The step S3 includes: calculating the angle of the current point relative to the reference center point; processing the case where the angle spans 360 degrees; and updating the angle buffer.

9. The detection method according to claim 7, characterized in that The step S4 includes: performing Gaussian blur processing on the image; converting the image into HSV color space; and applying a double threshold mask to extract the target object.

10. The detection method according to claim 7, characterized in that: The step S7 includes: calculating the RPM value based on the angle change and the time difference; optimizing the calculation result by applying a smoothing factor; and displaying the calculation result in real time.

Images